class-balanced-loss
Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019
Use a special loss function to improve the performance of models on imbalanced datasets in computer vision tasks.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeClass-Balanced Loss Based on Effective Number of Samples. CVPR 2019
class-balanced-loss has 615 stars on GitHub. It has been forked 68 times. class-balanced-loss is written mainly in Python. It has been in active development since 2018. class-balanced-loss is available under the MIT license. Its main topics are cloud-tpu, computer-vision, cvpr, cvpr2019.
What is class-balanced-loss?
Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019
Is class-balanced-loss open source?
class-balanced-loss is an open-source project. It is released under the MIT license.
Is class-balanced-loss free?
Yes. class-balanced-loss is free and open source — you can use, modify and self-host it.
What license does class-balanced-loss use?
class-balanced-loss is available under the MIT license.
What language is class-balanced-loss written in?
class-balanced-loss is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/richardaecn-class-balanced-loss.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.